{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T04:10:24Z","timestamp":1759205424928,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030590642"},{"type":"electronic","value":"9783030590659"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-59065-9_22","type":"book-chapter","created":{"date-parts":[[2020,9,10]],"date-time":"2020-09-10T07:22:15Z","timestamp":1599722535000},"page":"269-284","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Scalable Machine Learning on Popular Analytic Languages with Parallel Data Summarization"],"prefix":"10.1007","author":[{"given":"Sikder Tahsin","family":"Al-Amin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos","family":"Ordonez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,11]]},"reference":[{"issue":"3","key":"22_CR1","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.bdr.2015.04.001","volume":"2","author":"OY Al-Jarrah","year":"2015","unstructured":"Al-Jarrah, O.Y., Yoo, P.D., Muhaidat, S., Karagiannidis, G.K., Taha, K.: Efficient machine learning for big data: a review. Big Data Res. 2(3), 87\u201393 (2015)","journal-title":"Big Data Res."},{"key":"22_CR2","unstructured":"Arthur, D., Vassilvitskii, S.: k-means++: the advantages of careful seeding. In: Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA, pp. 1027\u20131035 (2007)"},{"issue":"3","key":"22_CR3","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/s10619-011-7082-y","volume":"29","author":"A Behm","year":"2011","unstructured":"Behm, A., et al.: ASTERIX: towards a scalable, semistructured data platform for evolving-world models. Distrib. Parallel Databases (DAPD) 29(3), 185\u2013216 (2011). \nhttps:\/\/doi.org\/10.1007\/s10619-011-7082-y","journal-title":"Distrib. Parallel Databases (DAPD)"},{"key":"22_CR4","unstructured":"Bradley, P., Fayyad, U., Reina, C.: Scaling clustering algorithms to large databases. In: Proceedings of the ACM KDD Conference, pp. 9\u201315 (1998)"},{"key":"22_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-030-27618-8_19","volume-title":"Database and Expert Systems Applications","author":"SUS Chebolu","year":"2019","unstructured":"Chebolu, S.U.S., Ordonez, C., Al-Amin, S.T.: Scalable machine learning in the R language using a summarization matrix. In: Hartmann, S., K\u00fcng, J., Chakravarthy, S., Anderst-Kotsis, G., Tjoa, A.M., Khalil, I. (eds.) DEXA 2019. LNCS, vol. 11707, pp. 247\u2013262. Springer, Cham (2019). \nhttps:\/\/doi.org\/10.1007\/978-3-030-27618-8_19"},{"key":"22_CR6","unstructured":"Dean, J., et al.: Large scale distributed deep networks. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 1232\u20131240 (2012)"},{"key":"22_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6868-4","volume-title":"Seamless R and C++ Integration with Rcpp","author":"D Eddelbuettel","year":"2013","unstructured":"Eddelbuettel, D.: Seamless R and C++ Integration with Rcpp. Springer, New York (2013). \nhttps:\/\/doi.org\/10.1007\/978-1-4614-6868-4"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Gemulla, R., Nijkamp, E., Haas, P., Sismanis, Y.: Large-scale matrix factorization with distributed stochastic gradient descent. In: Proceedings of the KDD, pp. 69\u201377 (2011)","DOI":"10.1145\/2020408.2020426"},{"issue":"12","key":"22_CR9","doi-asserted-by":"publisher","first-page":"1700","DOI":"10.14778\/2367502.2367510","volume":"5","author":"J Hellerstein","year":"2012","unstructured":"Hellerstein, J., et al.: The MADlib analytics library or MAD skills, the SQL. Proc. VLDB 5(12), 1700\u20131711 (2012)","journal-title":"Proc. VLDB"},{"key":"22_CR10","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/ACCESS.2014.2332453","volume":"2","author":"H Hu","year":"2014","unstructured":"Hu, H., Wen, Y., Chua, T., Li, X.: Toward scalable systems for big data analytics: a technology tutorial. IEEE Access 2, 652\u2013687 (2014)","journal-title":"IEEE Access"},{"key":"22_CR11","unstructured":"Lang, D.T., Lang, M.D.T.: Package \u2018RCurl\u2019 (2012)"},{"issue":"3","key":"22_CR12","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/s10619-014-7145-y","volume":"32","author":"F Li","year":"2014","unstructured":"Li, F., Nath, S.: Scalable data summarization on big data. Distrib. Parallel Databases 32(3), 313\u2013314 (2014). \nhttps:\/\/doi.org\/10.1007\/s10619-014-7145-y","journal-title":"Distrib. Parallel Databases"},{"key":"22_CR13","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.is.2016.04.006","volume":"63","author":"C Ordonez","year":"2016","unstructured":"Ordonez, C., Cabrera, W., Gurram, A.: Comparing columnar, row and array DBMSS to process recursive queries on graphs. Inf. Systems 63, 66\u201379 (2016)","journal-title":"Inf. Systems"},{"issue":"2","key":"22_CR14","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s10115-003-0141-6","volume":"7","author":"C Ordonez","year":"2004","unstructured":"Ordonez, C., Omiecinski, E.: Accelerating EM clustering to find high-quality solutions. Knowl. Inf. Syst. 7(2), 135\u2013157 (2004). \nhttps:\/\/doi.org\/10.1007\/s10115-003-0141-6","journal-title":"Knowl. Inf. Syst."},{"issue":"7","key":"22_CR15","doi-asserted-by":"publisher","first-page":"1906","DOI":"10.1109\/TKDE.2016.2545664","volume":"28","author":"C Ordonez","year":"2016","unstructured":"Ordonez, C., Zhang, Y., Cabrera, W.: The Gamma matrix to summarize dense and sparse data sets for big data analytics. IEEE Trans. Knowl. Data Eng. (TKDE) 28(7), 1906\u20131918 (2016)","journal-title":"IEEE Trans. Knowl. Data Eng. (TKDE)"},{"key":"22_CR16","unstructured":"Ostrouchov, G., Chen, W.C., Schmidt, D., Patel, P.: Programming with big data in R (2012). \nhttp:\/\/r-pbd.org\/"},{"key":"22_CR17","unstructured":"Rickert, J.: Big data analysis with revolution R enterprise. Revolution Analytics (2011)"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Schmidberger, M., Morgan, M., Eddelbuettel, D., Yu, H., Tierney, L., Mansmann, U.: State-of-the-art in parallel computing with R. J. Stat. Softw. 47 (2009)","DOI":"10.18637\/jss.v031.i01"},{"issue":"1","key":"22_CR19","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/1629175.1629197","volume":"53","author":"M Stonebraker","year":"2010","unstructured":"Stonebraker, M., et al.: MapReduce and parallel DBMSs: friends or foes? Commun. ACM 53(1), 64\u201371 (2010)","journal-title":"Commun. ACM"},{"issue":"2","key":"22_CR20","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/TBDATA.2015.2472014","volume":"1","author":"EP Xing","year":"2015","unstructured":"Xing, E.P., et al.: Petuum: a new platform for distributed machine learning on big data. IEEE Trans. Big Data 1(2), 49\u201367 (2015)","journal-title":"IEEE Trans. Big Data"},{"key":"22_CR21","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M., Shenker, S., Stoica, I.: Spark: cluster computing with working sets. In: HotCloud USENIX Workshop (2010)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, T., Ramakrishnan, R., Livny, M.: BIRCH: an efficient data clustering method for very large databases. In: Proceedings of the ACM SIGMOD Conference, pp. 103\u2013114 (1996)","DOI":"10.1145\/235968.233324"}],"container-title":["Lecture Notes in Computer Science","Big Data Analytics and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-59065-9_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,10]],"date-time":"2020-09-10T07:26:59Z","timestamp":1599722819000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-59065-9_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030590642","9783030590659"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-59065-9_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"11 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DaWaK","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Big Data Analytics and Knowledge Discovery","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bratislava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovakia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dawak2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.dexa.org\/dawak2020","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"77","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"15","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"14","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"19% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2-3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}